Fault positioning method, device and equipment of CIP cleaning system and storage medium

Abstract

The invention relates to the technical field of industrial production fault judgment, and discloses a fault positioning method, device and equipment for a CIP cleaning system and a storage medium, and the method comprises the steps: obtaining a fault propagation path of the CIP cleaning system, the fault propagation path indicating a propagation process of a fault in the CIP cleaning system in a sensor, and the fault propagation path indicating the propagation process of the fault in the sensor; the fault propagation path is obtained based on a target Boolean control network model, and the target Boolean control network model is established based on a fault signal source possibly received by each sensor; obtaining a target signal collected by a sensor in the CIP cleaning system; and determining the fault of the CIP cleaning system based on the target signal and the fault propagation path. According to the invention, the fault positioning efficiency and accuracy of the CIP cleaning system can be improved, so that the industrial production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial production technology fault judgment, and in particular to a fault locating method, device, equipment and storage medium for a CIP cleaning system. Background Art

[0002] CIP cleaning, or "cleaning in place", has the advantages of high cleaning quality and good repeatability, and is used in milk powder, dairy, beverage, pharmaceutical and other industries. During the CIP cleaning process, a certain link may fail to start normally, alkali preparation may be overtime, and other failures may occur, which may affect the entire cleaning process and even affect the quality of the overall process production. Therefore, timely and accurate fault location of the CIP cleaning system can help effectively prevent problems in production and improve production efficiency. Summary of the invention

[0003] In view of this, the present invention provides a CIP cleaning system fault location method, device, equipment and storage medium to solve the problem of low accuracy and low efficiency in CIP cleaning system fault location.

[0004] In a first aspect, the present invention provides a method for locating a fault in a CIP cleaning system, the method comprising:

[0005] Acquire a fault propagation path of the CIP cleaning system, wherein the fault propagation path indicates a propagation process of a fault in the CIP cleaning system in a sensor, wherein the fault propagation path is acquired based on a target Boolean control network model, wherein the target Boolean control network model is established based on a source of a fault signal that each sensor may receive;

[0006] Acquire a target signal collected by a sensor in the CIP cleaning system;

[0007] A fault of the CIP cleaning system is determined based on the target signal and the fault propagation path.

[0008] In an optional implementation manner, the fault propagation path is obtained by the following method:

[0009] Obtaining sources of fault signals that may be received by various sensors of the CIP cleaning system, wherein the sources of fault signals that may be received by various sensors of the CIP cleaning system are determined based on prior knowledge of the CIP cleaning system;

[0010] Based on the sources of fault signals that may be received by various sensors of the CIP cleaning system, an initial Boolean control network model of faults and sensor signals of the CIP cleaning system is established;

[0011] Converting the initial Boolean control network model into the target Boolean control network model in algebraic form;

[0012] Based on the output of the target Boolean control network model, each of the fault propagation paths is obtained.

[0013] In an optional implementation, the initial Boolean control network model is a logical relationship established based on Boolean values;

[0014] The step of converting the initial Boolean control network model into the target Boolean control network model in algebraic form comprises:

[0015] Obtaining a Boolean vector corresponding to the fault sequence number in the initial Boolean control network model;

[0016] Converting the Boolean values ​​in the initial Boolean control network model into Boolean vectors to convert the initial Boolean control network model into the target Boolean control network model;

[0017] The Boolean value includes a fault sequence number, a logic symbol or a sensor serving as a source of a fault signal.

[0018] In an optional implementation, converting the Boolean value in the initial Boolean control network model into a Boolean vector includes:

[0019] Using a semi-tensor product to convert the Boolean values ​​in the initial Boolean control network model into Boolean vectors, to obtain a fault propagation relational expression of each sensor;

[0020] On the basis of the fault propagation relation, the product extraction method is used to obtain the state transition expression to form the target Boolean control network model.

[0021] In an optional implementation manner, obtaining each of the fault propagation paths based on the output of the target Boolean control network model includes:

[0022] For each fault, a corresponding fault observer is introduced to record the fault propagation path based on the output of the target Boolean control network model.

[0023] In an optional implementation, for each fault, introducing a corresponding fault observer, and recording the fault propagation path based on the output of the target Boolean control network model, includes:

[0024] Iterating the state transition expression in the target Boolean control network model to obtain sensor signals of each sensor at each time;

[0025] For each fault, if the sensor signal no longer changes after the target time, then the propagation step length of the fault is obtained based on the target time and the initial time;

[0026] The fault propagation path is obtained based on the propagation step length of each fault and the output of the target Boolean control network model recorded by the fault observer.

[0027] In an optional embodiment, the fault location method of the CIP cleaning system further includes:

[0028] For the two fault observers corresponding to the two faults, if they are exactly the same, it is determined that the two faults are indistinguishable;

[0029] If the two fault observers corresponding to the two faults are not completely the same, it is determined that the two faults are distinguishable.

[0030] In an optional embodiment, the fault location method of the CIP cleaning system further includes:

[0031] Obtaining a cleaning process Boolean control network model of the CIP cleaning system;

[0032] For each fault, respectively determining the inputs of the cleaning process Boolean control network model and the target Boolean control network model;

[0033] Obtain a first model output of the cleaning process Boolean control network model based on the corresponding input iteration, and obtain a second model output of the target Boolean control network model based on the corresponding input iteration;

[0034] Compare the first model output and the second model output in order according to an iteration order;

[0035] If the first model output and the second model output obtained by iteration are not completely the same, it is determined that the fault propagates along the fault propagation path.

[0036] In a second aspect, the present invention provides a fault location device for a CIP cleaning system, the device comprising:

[0037] A fault propagation path acquisition module is used to acquire a fault propagation path of the CIP cleaning system, wherein the fault propagation path indicates a propagation process of a fault in the CIP cleaning system in a sensor, and the fault propagation path is acquired based on a target Boolean control network model, wherein the target Boolean control network model is established based on a source of a fault signal that may be received by each sensor;

[0038] A sensor signal acquisition module, used to acquire a target signal collected by a sensor in the CIP cleaning system;

[0039] A fault location module is used to determine the fault of the CIP cleaning system based on the target signal and the fault propagation path.

[0040] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the fault location method of the CIP cleaning system of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the fault locating method for a CIP cleaning system according to the first aspect or any corresponding embodiment thereof.

[0042] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the fault locating method for a CIP cleaning system according to the first aspect or any corresponding embodiment thereof.

[0043] The fault location method, device, equipment and storage medium of the CIP cleaning system provided by the embodiments of the present invention obtain the fault propagation path of the CIP cleaning system (specifically, the fault propagation path in the sensor) based on the target Boolean control network model, so that the fault position can be analyzed according to the response of the sensor in the fault propagation path, thereby achieving rapid and accurate fault location, avoiding the adverse effects of further propagation of the fault on the cleaning process, and thus improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 is a schematic flow chart of a fault location method for a CIP cleaning system according to an embodiment of the present invention;

[0046] Figure 2 is a schematic diagram of a CIP cleaning system according to an embodiment of the present invention;

[0047] Figure 3 is a schematic diagram of a CIP cleaning system fault propagation Boolean control network obtained according to an embodiment of the present invention;

[0048] Figure 4 is a structural block diagram of a fault location device for a CIP cleaning system according to an embodiment of the present invention;

[0049] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0051] The fault propagation analysis methods based on models include: directed graph model, Petri net model, cellular automaton model, and complex network model. However, directed graph and Petri net models cannot describe the coupling relationship between components and are difficult to analyze large complex systems. The cellular automaton model is a grid dynamics model that describes local spatial interactions and temporal causal relationships. In the modeling process, the object is required to be discrete, which has limitations in practical applications. Complex network modeling requires a comprehensive understanding of the system structure and operation mechanism. In summary, the above four fault propagation analysis methods have the problems of being unable to handle the coupling relationship between components, unable to handle continuous objects, and requiring high prior knowledge. Boolean network (also known as Boolean control network) as a kind of logic network can concisely describe nonlinear dynamic problems, that is, it can handle discrete objects, and can also discretize continuous objects for analysis. The decoupling of Boolean network state space and subspace can be used to solve the coupling problem between components. Therefore, the Boolean control network model is an effective method for analyzing fault propagation. Using the Boolean control network model to analyze the fault propagation of the CIP cleaning system can more concisely represent the relationship between the components of the system and provide new ideas for fault propagation analysis.

[0052] According to an embodiment of the present invention, an embodiment of a fault location method for a CIP cleaning system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of executable computer instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0053] In this embodiment, a fault location method for a CIP cleaning system is provided, which can be used for computer equipment. Figure 1 FIG. 1 is a flow chart of a fault location method for a CIP cleaning system according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0054] Step S101, obtaining a fault propagation path of the CIP cleaning system, wherein the fault propagation path indicates a propagation process of a fault in the CIP cleaning system in a sensor, and the fault propagation path is obtained based on a target Boolean control network model, and the target Boolean control network model is established based on a source of a fault signal that each sensor may receive.

[0055] In some optional specific implementations, the fault propagation path is obtained by the following method:

[0056] Step S001, obtaining sources of fault signals that may be received by various sensors of the CIP cleaning system, wherein the sources of fault signals that may be received by various sensors of the CIP cleaning system are determined based on prior knowledge of the CIP cleaning system.

[0057] Specifically, from the prior knowledge of CIP cleaning, it can be known that the CIP cleaning process mainly includes three steps: drinking water flushing, flake caustic soda solution heating and circulating flushing, and drinking water heating and circulating flushing. Different switch states of the corresponding valves correspond to different cleaning steps. At the same time, there are possible faults, such as water level detection device failure, cleaning time timer failure, and temperature sensor failure. Sensors are installed at each valve of the CIP cleaning system to receive signals from faults or other sensors. Assuming that faults will not occur or spread simultaneously during the cleaning process, and that faults will not cause other faults to occur, assume that the system has a total of m faults and n sensors.

[0058] Step S002: establishing an initial Boolean control network model of the faults and sensor signals of the CIP cleaning system based on the sources of the fault signals that may be received by the various sensors of the CIP cleaning system.

[0059] The initial Boolean control network model is in the form of a logical relationship. The specific logical relationship of the model is:

[0060]

[0061] Among them, sk is the kth sensor, Indicates that the signal received by the kth sensor may come from m k A fault, Indicates that the signal received by the kth sensor may come from n k Sensors, y k represents the network output, and ∨ represents the logical symbol or.

[0062] In the above model formula, although there are f1, f2, etc. in the logical relationship formula for the possible sources of the fault signal of each sensor, it does not mean that the fault signal received by each sensor may come from fault f1, fault f2, etc. The fault source of the fault signal received by each sensor varies according to the actual situation of the CIP cleaning system. Here it only means that the fault signal received by each sensor may come from multiple faults. Similarly, although there are s1(t), s2(t)... in the logical relationship formula for the possible sources of the fault signal of each sensor, it does not mean that the fault signal received by each sensor may come from sensor s1, sensor s2, etc. The other sensor sources of the fault signal received by each sensor vary according to the actual situation of the CIP cleaning system. Here it only means that the fault signal received by each sensor may come from multiple other sensors.

[0063] In the embodiment of the present invention, based on the prior knowledge of the CIP cleaning system, a Boolean control network model of fault propagation of the CIP cleaning system is established, and the relationship between each sensor of the CIP cleaning system and the fault signal is intuitively and concisely represented by logical relationship.

[0064] Step S003: converting the initial Boolean control network model into the target Boolean control network model in algebraic form.

[0065] As mentioned above, the initial Boolean control network model is a logical relationship established based on Boolean values.

[0066] In some optional specific implementations, step S003, namely, converting the initial Boolean control network model into the target Boolean control network model in algebraic form, includes:

[0067] Step S0031, obtaining the Boolean vector corresponding to the fault sequence number in the initial Boolean control network model.

[0068] When the fault i When it occurs, i=1,2,…,m, which is the fault sequence number. otherwise in represents the i-th column of the 2D unit matrix, the fault signal F i The expression is:

[0069]

[0070] Here, × is the symbol for the semi-tensor product. Here and in the following text, the power of the Boolean quantity is the semi-tensor product.

[0071] Step S0032, converting the Boolean values ​​in the initial Boolean control network model into Boolean vectors, so as to convert the initial Boolean control network model into the target Boolean control network model;

[0072] The Boolean value includes a fault sequence number, a logic symbol, or a sensor (specifically, a sensor identifier) ​​that is a source of a fault signal.

[0073] In some specific implementations, step S0032, converting the Boolean value in the initial Boolean control network model into a Boolean vector, includes:

[0074] Step S00321, using the semi-tensor product to convert the Boolean values ​​in the initial Boolean control network model into Boolean vectors, to obtain the fault propagation relation of each sensor.

[0075] Specifically, the kth sensor fault propagation relation (algebraic form) is:

[0076]

[0077] in, is the symbol for the tensor product, F k,i represents the kth sensor s k The signal received from the fault vector, S k,j represents the kth sensor s k The signal received from the sensor vector, I n Indicates n (n in the above formula = 2 l-2 )-dimensional identity matrix, M d is the structure matrix of the OR logical operator.

[0078] Step S00322, based on the fault propagation relation, use the product extraction method to obtain the state transition expression to form the target Boolean control network model.

[0079] Specifically, based on the above fault propagation relationship, the target Boolean control network model is obtained by using the Khatri-Rao product:

[0080]

[0081] Where ⊙ is the symbol of the Khatri-Rao product, M k is the product extractor corresponding to the kth fault vector, N k is the product extractor corresponding to the kth sensor vector, O k is the product extractor corresponding to the k-th output,

[0082] In an embodiment of the present invention, the Boolean control logic network (i.e., the initial Boolean control network model) established directly based on the prior knowledge of the CIP cleaning system is converted into an algebraic Boolean control network model (i.e., the target Boolean control network model), which can facilitate the output calculation of the model.

[0083] Step S004: obtaining each of the fault propagation paths based on the output of the target Boolean control network model.

[0084] In some optional specific implementations, step S004, i.e., obtaining each fault propagation path based on the output of the target Boolean control network model, includes:

[0085] Step S0041: for each fault, introduce a corresponding fault observer, and record the fault propagation path based on the output of the target Boolean control network model.

[0086] Specifically, for the i-th fault, the observer R is introduced i ={y i (t)|t=1,2,…,T i}, and use the output of the established CIP cleaning system fault propagation Boolean control network to record the fault propagation path; from the prior knowledge of the semi-tensor product, it can be known that the output of the Boolean control network is The subscript i indicates the occurrence of a fault f i , T i is the fault propagation step length.

[0087] In some optional specific implementations, step S0041, i.e., introducing a corresponding fault observer for each fault and recording the fault propagation path based on the output of the target Boolean control network model, includes:

[0088] Step S00411, iterating the state transition expression in the target Boolean control network model to obtain the sensor signal of each sensor at each time.

[0089] Specifically, the state transition expression in the target Boolean control network model is:

[0090]

[0091] make Then the target Boolean control network model can be expressed as:

[0092]

[0093]

[0094] in,

[0095] Iterate the state transfer expression to obtain the sensor signal at time t:

[0096] s(t)=(ΦF) t s(0)

[0097] Where s(0) is the sensor signal at the initial moment,

[0098] Step S00412: for each fault, if the sensor signal no longer changes after the target time, then the propagation step length of the fault is obtained based on the target time and the initial time.

[0099] Specifically, for the fault f i , there is a relationship:

[0100]

[0101] T i Fault i The propagation step length.

[0102] Step S00413, obtaining the fault propagation path based on the propagation step length of each fault and the output of the target Boolean control network model recorded by the fault observer.

[0103] Specifically, the inverse operation of the semi-tensor product is applied to the output of the target Boolean control network model to convert the sensor signal vector into a sensor number, and obtain the transmission path of the fault between sensors. The sensor number x can be obtained according to the following formula:

[0104]

[0105] Some optional specific implementations also include:

[0106] For the two fault observers corresponding to the two faults, if they are exactly the same, it is determined that the two faults are indistinguishable;

[0107] If the two fault observers corresponding to the two faults are not completely the same, it is determined that the two faults are distinguishable.

[0108] For example, the set symmetric difference can be used to determine whether any two faults are distinguishable. Specifically, for any two faults f i ,f j , the propagation step lengths are T i ,T j , let T max =max{T i ,T j}, and the corresponding fault propagation observers are:

[0109] R i ={y i (1),y i (2),…,y i (T i )}

[0110] R j ={y j (1),y j (2),…,y j (T j )}

[0111] For the set R i ,R j , if there exists a step length t such that there are different elements in the two, that is, there exists 0<t≤T m ,t∈N, so that y i (t i )≠y j (t j ) holds true, it means that any two faults can be distinguished. Using set language, the fault distinguishability condition is expressed as follows:

[0112] right If the fault f i ,f j distinguishable;

[0113] Where Δ represents the symmetric difference of sets. For sets A and B, AΔB=A∪BA∩B.

[0114] If it is determined at time t that the two faults can be distinguished, the process ends; otherwise, the process continues to determine time t+1 until T max The judgment step ends and the conclusion is that the two cannot be distinguished.

[0115] In addition, after obtaining the fault propagation path of the CIP cleaning system, the embodiment of the present invention further includes a process of demonstrating the fault propagation path.

[0116] In some optional specific implementations, the process of demonstrating the fault propagation path includes:

[0117] Obtaining a cleaning process Boolean control network model of the CIP cleaning system;

[0118] For each fault, respectively determining the inputs of the cleaning process Boolean control network model and the target Boolean control network model;

[0119] Obtain a first model output of the cleaning process Boolean control network model based on the corresponding input iteration, and obtain a second model output of the target Boolean control network model based on the corresponding input iteration;

[0120] Compare the first model output and the second model output in order according to an iteration order;

[0121] If the first model output and the second model output obtained by iteration are not completely the same, it is determined that the fault propagates along the fault propagation path.

[0122] In an embodiment of the present invention, the fault propagation path can be demonstrated for each possible fault in the CIP cleaning system. The inputs of the cleaning process Boolean control network model and the target Boolean control network model are different for different faults. The maximum number of iterations of the first model output and the second model output can be equal to the propagation step length of the corresponding fault.

[0123] Specifically, the cleaning process Boolean control network model of the CIP cleaning system can be:

[0124]

[0125] in, is the state quantity, For input, is the output, L and H are the state transfer matrix and output matrix of the process Boolean control network respectively.

[0126] For one of the faults, given the initial state and input sequence, the output obtained by the cleaning process Boolean control network (i.e., the first model output) is taken as the known output. If the known output is different from the output obtained by the target Boolean control network model, it means that the fault is recognized by the target Boolean control network model, which means that the fault propagates along the obtained propagation path, that is, the above-mentioned fault propagation analysis method is correct.

[0127] Step S102, obtaining a target signal collected by a sensor in the CIP cleaning system.

[0128] Step S103: determining the fault of the CIP cleaning system based on the target signal and the fault propagation path.

[0129] If the half tensor product inverse operation is used, the fault propagation path is:

[0130]

[0131] Assume that during the actual cleaning process, the sensor fails. like right All of them are established, then we can The fault location is obtained k .like make Further judgement and Are they equal? ​​If In the second step of sensor abnormality The fault location is obtained k .

[0132] The fault location method for the CIP cleaning system provided in this embodiment obtains the fault propagation path of the CIP cleaning system (specifically, the fault propagation path in the sensor) based on the target Boolean control network model, so that the fault position can be analyzed according to the response of the sensor in the fault propagation path, thereby achieving rapid and accurate fault location, avoiding the adverse effects of further propagation of the fault on the cleaning process, and thus improving production efficiency.

[0133] In this embodiment, a fault location method for a CIP cleaning system is provided, which is applied to Figure 2 The CIP cleaning system shown in the figure, the fault location method comprises the following steps:

[0134] Step 1: Using the prior knowledge of the CIP cleaning system, the semi-tensor product method and product extraction method are used to model the faults and sensors;

[0135] Figure 2 The cleaning process of the CIP cleaning system shown is:

[0136] After receiving the cleaning instruction, start cleaning, open the drinking water valve in the CIP cleaning pipeline and the liquid outlet valve at the bottom of the concentration tank, rinse the inner wall and bottom cover of the tank, and discharge the rinse water to the storage tank. After 30 minutes of rinsing, close the drinking water valve and liquid outlet valve of the CIP cleaning system; open the flake alkali solution valve in the CIP cleaning pipeline on the concentration tank, and wait until the flake alkali solution capacity in the tank meets the equipment requirements, and then close the flake alkali solution valve of the CIP pipeline; open the circulation pipeline valve and liquid medicine pump. If the temperature sensors at the bottom and side of the tank show that the temperature in the concentration tank is less than 60 degrees Celsius, open the steam valve, heat the circulation process, and close the steam valve when the temperature reaches 60 degrees Celsius; close the circulation pipeline valve and liquid medicine pump after 30 minutes of circulation cleaning; open the concentration Open the liquid outlet valve at the bottom of the shrink tank to discharge the cleaning water to the storage tank; open the drinking water valve of the CIP cleaning pipeline of the concentration tank, and wait until the drinking water capacity in the tank meets the equipment requirements, and then close the CIP pipeline drinking water valve; open the circulation pipeline valve and the liquid pump, open the steam valve to heat the circulation process, heat the temperature to 60 degrees Celsius and close the steam valve; close the circulation pipeline valve and the liquid pump after 30 minutes of circulation cleaning; open the liquid outlet valve at the bottom of the concentration tank to discharge the cleaning water to the storage tank; if the tank bottom cleaning liquid detection device shows that the cleaning water has met the requirements, the equipment stops and the cleaning is completed; otherwise, open the drinking water valve of the CIP pipeline of the concentration tank again, add enough water, heat the circulation cleaning, and drain the liquid until the cleaning water meets the cleaning requirements.

[0137] Assume that the CIP cleaning system has a total of 5 sensors, namely: the concentration tank CIP cleaning drinking water valve, the concentration tank CIP cleaning flake alkali liquid valve, the circulation pipeline valve, the concentration tank bottom outlet valve and the concentration tank bottom and lower steam valve sensors, corresponding to sensor numbers 1-5, represented by s1-s5, respectively. There are 4 possible faults, namely: water level detector failure, concentration tank bottom cleaning liquid turbidity detection device failure, cleaning timer failure and temperature sensor failure, corresponding to fault numbers 1-4, represented by f1-f4. The schematic diagram of the CIP cleaning equipment and valves in this example is as follows Figure 2 shown.

[0138] After analyzing the above five sensors and four faults, the system Boolean control network model is obtained as follows:

[0139]

[0140] Step 2: Convert the fault sequence number into a Boolean vector and use it as the input of the model. Use the semi-tensor product method and product extraction method to convert the Boolean control network model into an algebraic form.

[0141] (1) When the fault f i When it occurs, i=1,2,…,m, which is the fault sequence number. otherwise in represents the i-th column of the 2D unit matrix, the fault signal F i The expression is:

[0142]

[0143] in, is the symbol for the semi-tensor product. Here and in the following text, all powers of Boolean quantities are semi-tensor products.

[0144] According to the corresponding relationship between fault and serial number in step 1, the fault signals are:

[0145]

[0146] (2) Convert the logical symbols into Boolean vectors, and use the semi-tensor product method to convert the Boolean control network model into algebraic form, and obtain the fault propagation relation of the kth sensor:

[0147]

[0148] in, is the symbol for the tensor product, F k,i represents the kth sensor s k The signal received from the fault vector, S k,j represents the kth sensor s kThe signal received from the sensor vector, I n represents the n-dimensional identity matrix, M d is the structure matrix of the OR logical operator.

[0149] correspond Figure 2 The state transition relationship between the five sensors and four faults of the CIP cleaning system shown is:

[0150]

[0151] Using the product extraction method and the Khatri-Rao product, the fault propagation Boolean control network model of the CIP cleaning system is obtained as follows:

[0152]

[0153] Where ⊙ is the symbol of the Khatri-Rao product, M k is the product extractor corresponding to the kth fault vector, N k is the product extractor corresponding to the kth sensor vector, O k is the product extractor corresponding to the k-th output,

[0154] Corresponding to Figure 2 The linear expression of the Boolean control network relationship between the five sensors and four faults of the CIP cleaning system shown is:

[0155]

[0156] y(t)=I 32 s(t)

[0157] Step 3: Introduce a fault propagation observer to record each fault propagation path;

[0158] For the i-th fault, the observer R is introduced i ={y i (t)|t=1,2,…,T i}, and use the output of the established CIP cleaning system fault propagation Boolean control network to record the fault propagation path; from the prior knowledge of the semi-tensor product, it can be known that the output of the Boolean control network is The subscript i indicates the occurrence of a fault f i , T i is the fault propagation step length, which is defined as follows:

[0159]

[0160] The network model can be expressed as:

[0161]

[0162] in,

[0163] Iterate the state transfer expression to obtain the sensor signal at time t:

[0164] s(t)=(ΦF) t s(0)

[0165] Where s(0) is the sensor signal at the initial moment,

[0166] For fault f i , there is a relationship:

[0167]

[0168] T i Fault i The propagation step length;

[0169] From step one and step two, the semi-tensor product method is used to calculate the four fault propagation step lengths in step one:

[0170] T1=3,T2=3,T3=2,T4=1

[0171] The inverse operation of the semi-tensor product is used to convert the vector into a serial number, which is convenient for analyzing the fault propagation of the CIP cleaning system. The sensor serial number x can be obtained according to the following relationship:

[0172]

[0173] From step 1 to step 3, each fault observer is obtained as:

[0174]

[0175] Using the semi-tensor product inverse operation, four fault propagation paths are obtained:

[0176]

[0177] Fault propagation diagram Figure 3 shown.

[0178] Step 4: Use the set symmetric difference to determine whether any two faults are distinguishable;

[0179] For any two faults f i ,f j , the propagation step lengths are T i ,T j , let T max =max{T i ,T j}, and the corresponding fault propagation observers are:

[0180] R i ={y i (1),y i (2),…,y i (T i )}

[0181] R j ={y j (1),y j (2),…,y j (T j )}

[0182] For the set R i ,R j , if there exists a step length t such that there are different elements in the two, that is, there exists 0<t≤T m ,t∈N, so that y i (t i )≠y j (t j ) holds true, it means that any two faults can be distinguished. Using set language, the fault distinguishability condition is expressed as follows:

[0183] right If the fault f i ,f j distinguishable;

[0184] Where Δ represents the symmetric difference of sets. For sets A and B, AΔB=A∪BA∩B.

[0185] If it is determined at time t that the two faults can be distinguished, the process ends; otherwise, the process continues to determine time t+1 until T max The judgment step ends and the conclusion is that the two cannot be distinguished.

[0186] It can be seen from step three that for any two of the above four faults, the sensor signals obtained at t=1 are all different, so these four faults can be distinguished through the model established and the method used in this example.

[0187] Step 5: Use fault identification to demonstrate the proposed fault propagation analysis method;

[0188] Establish the Boolean control network model of CIP cleaning process:

[0189]

[0190] in, is the state quantity, For input, Output, L and H are the state transfer matrix and output matrix of the process Boolean control network respectively,

[0191] Given the initial state and input sequence, the output obtained by the process Boolean control network is taken as the known output; the state transfer matrix and output matrix of the known fault propagation Boolean control network are different. If the known output is different from the output obtained by the fault propagation network, it means that there is a fault in the propagation network and it is identified, indicating that the fault propagates along the obtained propagation path, that is, the fault propagation analysis method is correct; the specific demonstration algorithm is as follows:

[0192] Known: Input and output sequence of the cleaning process Boolean control network, initial state;

[0193] Initialization: τ = 0;

[0194] Iteration:

[0195] Judgment: If the calculated output is the same as the known cleaning process Boolean control network output, continue to iterate; otherwise, terminate the algorithm and conclude that there is a fault in the fault propagation network and it is identified, the fault propagates along the obtained propagation path, and the fault propagation analysis method is correct.

[0196] Given: Input sequence: Output sequence:

[0197] Initialization: τ = 0;

[0198] Iteration:

[0199]

[0200] It can be seen that when t=1, it is identified that the fault propagation network has a fault, which indicates that the fault propagation analysis method is correct.

[0201] Step 6: After obtaining the fault signal output by the sensor, the fault is located based on the transmission path of the fault between the sensors.

[0202] In this embodiment, a fault location device for a CIP cleaning system is also provided, which is used to implement the above-mentioned embodiments and preferred implementations, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0203] This embodiment provides a fault location device for a CIP cleaning system. Figure 4 As shown, including:

[0204] A fault propagation path acquisition module 401 is used to acquire a fault propagation path of the CIP cleaning system, wherein the fault propagation path indicates a propagation process of a fault in the CIP cleaning system in a sensor, and the fault propagation path is acquired based on a target Boolean control network model, wherein the target Boolean control network model is established based on a source of a fault signal that each sensor may receive;

[0205] A sensor signal acquisition module 402 is used to acquire a target signal collected by a sensor in the CIP cleaning system;

[0206] The fault location module 403 is used to determine the fault of the CIP cleaning system based on the target signal and the fault propagation path.

[0207] In some optional embodiments, the fault location device of the CIP cleaning system further includes:

[0208] A fault signal source acquisition module, used to acquire the source of the fault signal that each sensor of the CIP cleaning system may receive, wherein the source of the fault signal that each sensor of the CIP cleaning system may receive is determined based on prior knowledge of the CIP cleaning system;

[0209] A fault transmission model building module, used to build an initial Boolean control network model of faults and sensor signals of the CIP cleaning system based on sources of fault signals that may be received by various sensors of the CIP cleaning system;

[0210] A conversion module, used for converting the initial Boolean control network model into the target Boolean control network model in algebraic form;

[0211] The propagation path acquisition module is used to obtain each fault propagation path based on the output of the target Boolean control network model.

[0212] In some optional specific implementations, the initial Boolean control network model is a logical relationship established based on Boolean values;

[0213] The conversion module comprises:

[0214] A fault Boolean vector acquisition unit, used to acquire a Boolean vector corresponding to a fault sequence number in the initial Boolean control network model;

[0215] A conversion unit, used for converting the Boolean values ​​in the initial Boolean control network model into Boolean vectors, so as to convert the initial Boolean control network model into the target Boolean control network model;

[0216] The Boolean value includes a fault sequence number, a logic symbol or a sensor serving as a source of a fault signal.

[0217] In some optional specific embodiments, the conversion unit is specifically used to use a semi-tensor product to convert the Boolean values ​​in the initial Boolean control network model into Boolean vectors to obtain the fault propagation relationship of each sensor; based on the fault propagation relationship, the product extraction method is used to obtain the state transition expression to form the target Boolean control network model.

[0218] In some optional specific implementations, the propagation path acquisition module is specifically used to introduce a corresponding fault observer for each fault, and record the fault propagation path based on the output of the target Boolean control network model.

[0219] In some optional specific implementations, the propagation path acquisition module includes:

[0220] An iteration unit, used for iterating the state transition expression in the target Boolean control network model to obtain sensor signals of each sensor at each time;

[0221] A fault propagation step length determining unit, for each fault, if the sensor signal no longer changes after a target time, then obtains the propagation step length of the fault based on the target time and an initial time;

[0222] A path acquisition unit is used to obtain the fault propagation path based on the propagation step length of each fault and the output of the target Boolean control network model recorded by the fault observer.

[0223] In some optional embodiments, the fault location device of the CIP cleaning system further includes:

[0224] A first judgment unit, configured to determine that the two faults are indistinguishable if the two fault observers corresponding to the two faults are completely identical;

[0225] The second judgment unit is configured to determine that the two faults are distinguishable if the two fault observers corresponding to the two faults are not completely the same.

[0226] In some optional embodiments, the fault location device of the CIP cleaning system further includes:

[0227] A process model acquisition module, used to acquire a Boolean control network model of a cleaning process of the CIP cleaning system;

[0228] A model input acquisition module, used to determine the inputs of the cleaning process Boolean control network model and the target Boolean control network model respectively for each fault;

[0229] A model output acquisition module, used to acquire a first model output of the cleaning process Boolean control network model obtained by iteration based on a corresponding input, and to acquire a second model output of the target Boolean control network model obtained by iteration based on a corresponding input;

[0230] A comparison module, used for comparing the first model output and the second model output in sequence according to an iteration order;

[0231] A determination module is used to determine that the fault is propagated along the fault propagation path if the first model output and the second model output obtained by iteration are not completely the same.

[0232] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0233] The fault location device of the CIP cleaning system in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0234] The embodiment of the present invention also provides a computer device having the above Figure 4 The fault locating device of the CIP cleaning system is shown.

[0235] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0236] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0237] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0238] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0239] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0240] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0241] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0242] The computer device also includes a communication interface, which is used for the computer device to communicate with other devices or a communication network.

[0243] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0244] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0245] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A fault location method for a CIP cleaning system, characterized in that: The method comprises: Acquire a fault propagation path of the CIP cleaning system, wherein the fault propagation path indicates a propagation process of a fault in the CIP cleaning system in a sensor, wherein the fault propagation path is acquired based on a target Boolean control network model, wherein the target Boolean control network model is established based on a source of a fault signal that each sensor may receive; Acquire a target signal collected by a sensor in the CIP cleaning system; A fault of the CIP cleaning system is determined based on the target signal and the fault propagation path.

2. The method according to claim 1, characterized in that The fault propagation path is obtained by the following method: Obtaining sources of fault signals that may be received by various sensors of the CIP cleaning system, wherein the sources of fault signals that may be received by various sensors of the CIP cleaning system are determined based on prior knowledge of the CIP cleaning system; Based on the sources of fault signals that may be received by various sensors of the CIP cleaning system, an initial Boolean control network model of faults and sensor signals of the CIP cleaning system is established; Converting the initial Boolean control network model into the target Boolean control network model in algebraic form; Based on the output of the target Boolean control network model, each of the fault propagation paths is obtained.

3. The method according to claim 2, characterized in that The initial Boolean control network model is a logical relationship established based on Boolean values; The step of converting the initial Boolean control network model into the target Boolean control network model in algebraic form comprises: Obtaining a Boolean vector corresponding to the fault sequence number in the initial Boolean control network model; Converting the Boolean values ​​in the initial Boolean control network model into Boolean vectors to convert the initial Boolean control network model into the target Boolean control network model; The Boolean value includes a fault sequence number, a logic symbol or a sensor serving as a source of a fault signal.

4. The method according to claim 3, characterized in that The step of converting the Boolean value in the initial Boolean control network model into a Boolean vector comprises: Using a semi-tensor product to convert the Boolean values ​​in the initial Boolean control network model into Boolean vectors, to obtain a fault propagation relational expression of each sensor; On the basis of the fault propagation relation, the product extraction method is used to obtain the state transition expression to form the target Boolean control network model.

5. The method according to claim 4, characterized in that The output based on the target Boolean control network model, obtaining each fault propagation path, comprises: For each fault, a corresponding fault observer is introduced to record the fault propagation path based on the output of the target Boolean control network model.

6. The method according to claim 5, characterized in that For each fault, a corresponding fault observer is introduced, and the fault propagation path is recorded based on the output of the target Boolean control network model, including: Iterating the state transition expression in the target Boolean control network model to obtain sensor signals of each sensor at each time; For each fault, if the sensor signal no longer changes after the target time, then the propagation step length of the fault is obtained based on the target time and the initial time; The fault propagation path is obtained based on the propagation step length of each fault and the output of the target Boolean control network model recorded by the fault observer.

7. The method according to claim 6, characterized in that Also includes: For the two fault observers corresponding to the two faults, if they are exactly the same, it is determined that the two faults are indistinguishable; If the two fault observers corresponding to the two faults are not completely the same, it is determined that the two faults are distinguishable.

8. The method according to any one of claims 2 to 7, characterized in that: Also includes: Obtaining a cleaning process Boolean control network model of the CIP cleaning system; For each fault, respectively determining the inputs of the cleaning process Boolean control network model and the target Boolean control network model; Obtain a first model output of the cleaning process Boolean control network model based on the corresponding input iteration, and obtain a second model output of the target Boolean control network model based on the corresponding input iteration; Compare the first model output and the second model output in order according to an iteration order; If the first model output and the second model output obtained by iteration are not completely the same, it is determined that the fault propagates along the fault propagation path.

9. A fault location device for a CIP cleaning system, characterized in that: The device comprises: A fault propagation path acquisition module is used to acquire a fault propagation path of the CIP cleaning system, wherein the fault propagation path indicates a propagation process of a fault in the CIP cleaning system in a sensor, and the fault propagation path is acquired based on a target Boolean control network model, wherein the target Boolean control network model is established based on a source of a fault signal that may be received by each sensor; A sensor signal acquisition module, used to acquire a target signal collected by a sensor in the CIP cleaning system; A fault location module is used to determine the fault of the CIP cleaning system based on the target signal and the fault propagation path.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the fault locating method for the CIP cleaning system according to any one of claims 1 to 8 by executing the computer instructions.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the fault locating method for a CIP cleaning system according to any one of claims 1 to 8.

12. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the fault locating method for a CIP cleaning system according to any one of claims 1 to 8.

Images